Greetings! welcome back Tech on: AyeA pop-up newsletter that teaches you about Artificial Intelligence, how it works and how to use it.
In last week’s newsletter, I shared Golden tips for getting the most useful answers from chatbots Such as ChatGPT, Bing and Bard. Now that you’re familiar with the general principle of building relationships with AI – the more specific and detailed instructions you give, the better results you’ll get – let’s move into a slightly different area.
Much of the hype and fear surrounding generative AI has been about text. But there have also been rapid and dramatic developments in the systems that can generate the images. In many respects, these share a similar structure to text-based generative AI, but they can also be much wackier – and lend themselves to some pretty fun creative pursuits.
Image generators are trained on billions of images, enabling them to create new compositions that were once the sole domain of painters and other artists. Sometimes Experts can’t tell the difference between AI-generated images and real photos (a circumstance that has fueled dangerous misinformation campaigns in addition to funny creations). And these tools are already changing the way creative professionals doing their jobs,
Compared to products like ChatGPT, the image generating AI tools are not as advanced. They require jumping through a few more hoops, and that can cost some money. But if you’re interested in learning the ropes, there’s no better time to start.
Last week, Adobe added a generative AI feature to the beta version of Photoshop, its iconic graphics software, and creators on social networks like TikTok and Instagram have been buzzing about it ever since.
I have a lot of experience with photoshop. When I tested the new feature, called “Generative Fill,” I was impressed by how quickly and efficiently the AI performed tasks that would have taken me at least an hour to complete . In less than five minutes and with just a few clicks, I was able to use the feature to remove objects, add objects, and swap backgrounds.
(To experiment with these tools yourself, start by signing up for a free trial.) adobe creative suite, Then, install the new Adobe Photoshop beta, which includes Generative Fill.)
Once you have the Photoshop beta installed, import a photo and try these tricks:
to change a background, click the “Object Selection” icon (it has an arrow pointing over a box), then under the Selection menu, click “Invert” to select the background. Next click the “Generative Fill” box and type in one at the prompt — or leave it blank to let Photoshop come up with a new background concept for you.
I used these steps to edit a photo of my Corgi, Max. I typed in “kennel” for the prompt, and clicked “Generate” to change the background. Here’s the before (left) and after.
The New York Times photo editor does not enhance or alter photos, or generate images using artificial intelligence. But my first thought after testing out Generative Fill was that photo editors working in other contexts, such as marketing, may soon be out of work. when i shared it Adobe’s chief technology officer, Eli Greenfield, said in theory that it could make photo editing more accessible, but he was optimistic that humans would still be needed.
“I can make really beautiful pictures with it, but frankly, I still make boring pictures,” he said. “When I look at the content that artists create when you hold it in their hands versus what I create, their content is much more interesting because they know how to tell a story.”
I admit that what I’ve done with Generative Fill is far less exciting than what other people post on social media. Lorenzo Green, who tweets about AI, posted a collage of famous album covers, including Michael Jackson’s “Thriller” and Adele’s “21”, which were extended with generative fills. The results were quite interesting.
(A note: If setting up Photoshop seems daunting, there’s a faster way to test out Adobe’s AI adobe firefly website, There, you can open the generative fill tool, upload an image, and click the “Add” tool to explore a subject, such as a dog. Then click on “Background” and type in a hint like “beach”.)
more image generator
tools like Dal-e And can create entirely new images in midjourney seconds. They work similar to chatbots: you type into a text prompt – the more specific, the better.
To write a quality prompt, start with the medium you want to emulate, followed by the topic and any additional details. For example, typing “picture of a cat wearing a sweater in a brightly lit room” DALL-E prompt box will generate something like this:
DALL-E, which is owned by Open AI, the makers of ChatGPT, was one of the first widely available AI image generators that was simple for people to use. For $15, you get 115 credits; One credit can be used to make a set of four images.
Midjourney, another popular image generator, is a work in progress, so the user experience isn’t as polished. The service costs $10 a month, and entering a hint can be a bit more complicated, as it requires joining Discord, a separate messaging app. Nonetheless, the project can produce high-quality, realistic images.
to use it, join the brawl And then Request an invite to Midjourney Server, After joining the server, inside the chat box, type “/imagine” followed by a prompt. I typed in “imagine a manga cover of a corgi in a ninja turtle costume” and produced a set of convincing images:
While typing a basic request is fine, some have found obscure prompts that produce extraordinary results (Beeboom, a tech blog, a list of examples, at Columbia University, Lance Weiler is Teaching students to take advantage of AIincluding midjourney to create the artwork.
Whatever device you use, keep in mind that it is your responsibility to use this technology responsibly. Technologists warn that image generators could increase the spread of deepfakes and misinformation. But the tools can also be used in positive and creative ways, like making family photos look better and brainstorming artistic concepts.
What will happen next?
Next week, I’ll share some tips on how to use AI to speed up aspects of office jobs, such as drafting talking points and creating presentation slides.
In case you’re wondering, the delightfully insane image at the top of this newsletter was created by a human – the painter charles desmarais – not by AI